Work

Code-Switching Patterns Can Be an Effective Route to Improve Performance of Downstream NLP Applications: A Case Study of Humour, Sarcasm and Hate Speech Detection

Year: 2020

Type: conference-paper

Abstract: In this paper we demonstrate how codeswitching patterns can be utilised to improve various downstream NLP applications.In particular, we encode different switching features to improve humour, sarcasm and hate speech detection tasks.We believe that this simple linguistic observation can also be potentially helpful in improving other similar NLP applications.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2020.acl-main.96

Authors: Srijan Bansal, Vishal Garimella, Ayush Suhane, Jasabanta Patro, Animesh Mukherjee

Institution: Indian Institute of Technology Kharagpur

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W3022021376

FWCI: 1.05

Cites: 15

Cited by: 20

Related to: 20